Production visibility through logs, metrics, traces, and alerting — the three pillars of observability
You are a monitoring and observability expert specializing in implementing comprehensive monitoring solutions.
You are an SLO (Service Level Objective) expert specializing in implementing reliability standards and error budget-based engineering practices.
Observability: structured logging, metrics (RED/USE/four golden signals), distributed tracing (OpenTelemetry), correlation IDs, log aggregation, SLO/SLI.
Observability and SRE expert. Use when setting up monitoring, logging, tracing, defining SLOs, or managing incidents.
Monitor, observe, and report on infrastructure health, application metrics, and system observability.
Top-level workflow skill for USD performance diagnosis and optimization. Use for slow loading, high memory, low FPS, or 'optimize my scene' requests; delegates auth/runtime setup…
Optimize OneNote Graph API performance for large notebooks, image handling, and batch operations. Use when dealing with slow API responses, large notebooks, image uploads, or HTTP…
Migrate OneNote integrations across Graph SDK versions, auth deprecations, and API changes. Use when upgrading Graph SDK, migrating from app-only to delegated auth, or handling…
Implement change detection for OneNote using polling and delta queries (webhooks decommissioned June 2023).
Diagnose and fix OpenEvidence common errors. Trigger: "openevidence error", "fix openevidence", "debug openevidence".
Create a minimal working OpenEvidence example. Trigger: "openevidence hello world", "openevidence example", "test openevidence".
Install and configure OpenEvidence SDK/API authentication. Use when setting up a new OpenEvidence integration.
Migration Deep Dive for OpenEvidence. Trigger: "openevidence migration deep dive".
Performance Tuning for OpenEvidence. Trigger: "openevidence performance tuning".
Set up OpenRouter API authentication and configure API keys. Use when starting a new OpenRouter integration, rotating keys, or troubleshooting auth issues.
Avoid common OpenRouter integration mistakes and gotchas. Use proactively when starting a new integration or reviewing existing code.
Optimize OpenRouter request latency and throughput. Use when building real-time applications, reducing TTFT, or scaling request volume.
Migrate to OpenRouter from direct provider APIs or upgrade between SDK/model versions. Triggers: 'openrouter migrate', 'openrouter upgrade', 'switch to openrouter', 'migrate from…
Diagnose and fix Oracle Cloud Infrastructure API errors with real error codes and proven fixes. Use when encountering OCI ServiceError exceptions, auth failures, SSL issues, or…
Track OCI spend with the Usage API and set up budget alerts. Use when monitoring Oracle Cloud costs, creating budgets, analyzing spend by compartment or service, or optimizing…
Manage OCI Object Storage — buckets, uploads, PARs, and lifecycle policies. Use when uploading objects, creating pre-authenticated requests, or configuring lifecycle rules.
Set up a productive local OCI development workflow using CLI and SDK instead of the web console. Use when the OCI Console is too slow, setting up CLI profiles, or building shell…
Set up programmatic monitoring, logging, and alarms for OCI resources. Use when configuring OCI Monitoring metrics, creating alarm rules, publishing custom metrics, or searching…
Optimize OCI compute shapes, block volume tiers, and network throughput. Use when choosing instance shapes, configuring block volume performance, or benchmarking OCI…
Wire up event-driven workflows with OCI Events, Notifications, and Functions. Use when building serverless event processing, subscribing to instance lifecycle changes, or routing…
Use this when working with OpenTelemetry, telemetry, observability, traces, spans, metrics, logs, OTLP, semantic conventions, or instrumentation.
Analyze OVHcloud Public Cloud cost posture across projects and regions: identify idle instances and unattached volumes, review Savings Plans and commitment coverage, recommend…
Use for OZM-managed logging, metrics, traces, alerts, SLO, error reporting, or runtime diagnosis work.
Optimize Palantir Foundry costs through compute tuning, incremental builds, and usage monitoring. Use when analyzing Foundry compute costs, reducing API usage, or implementing…
Implement Palantir Foundry data handling with PII protection, markings, and GDPR compliance. Use when handling sensitive data in Foundry, implementing data classifications, or…
Configure Palantir Foundry enterprise access control with project roles, markings, and service users.
Execute major Palantir Foundry migration strategies including data migration, API version upgrades, and platform transitions.
Set up observability for Palantir Foundry integrations with metrics, logging, and alerts. Use when implementing monitoring for Foundry API calls, setting up dashboards, or…
Implement Palantir Foundry webhook handling for Ontology change events. Use when reacting to Ontology object changes, dataset updates, or build completion events from Foundry.
Use when declaring, measuring, or enforcing performance thresholds as a quality contract rather than as an aspirational target.
Diagnoses pipeline performance issues -- slow jobs, expensive queries, latency trends -- using Monte Carlo's cross-platform observability.
Install and configure Perplexity Sonar API authentication. Use when setting up a new Perplexity integration, configuring API keys, or initializing the OpenAI-compatible client for…
Identify and avoid Perplexity anti-patterns and common integration mistakes. Use when reviewing Perplexity code, onboarding new developers, or auditing existing integrations for…
Load test Perplexity Sonar API integrations and plan capacity. Use when running performance tests, planning for traffic growth, or benchmarking Perplexity latency under load.
Migrate to Perplexity Sonar from other search/LLM APIs using the strangler fig pattern. Use when switching from Google Custom Search, Bing API, or other LLMs to Perplexity, or…
Configure Perplexity Sonar API across development, staging, and production environments. Use when setting up multi-environment search integrations, managing API keys per…
Set up monitoring for Perplexity Sonar API with latency, cost, citation quality, and error tracking. Use when implementing monitoring dashboards, setting up alerts, or tracking…
Implement content moderation, model selection policy, citation quality enforcement, and per-user usage quotas for Perplexity Sonar API.
Implement reliability patterns for Perplexity Sonar API: circuit breaker, model fallback, streaming timeout, and citation validation.
Migrate between Perplexity model generations and API parameter changes. Use when upgrading to new Sonar models, handling deprecated parameters, or migrating from legacy pplx-api…
Fix top Persona API errors: 401, 422, webhook signature failures, inquiry state issues. Use when working with Persona identity verification.
Local development with Persona sandbox, ngrok for webhooks, mock verifications. Use when working with Persona identity verification.
Upgrade Persona API versions and handle breaking changes. Use when working with Persona identity verification.
Handle Persona webhook events for inquiry and verification status changes. Use when working with Persona identity verification.
OpenInference semantic conventions and instrumentation for Phoenix AI observability. Use when implementing LLM tracing, creating custom spans, or deploying to production.
Podium common errors — business messaging and communication platform integration. Use when working with Podium API for messaging, reviews, or payments.
Podium cost tuning — business messaging and communication platform integration. Use when working with Podium API for messaging, reviews, or payments.
Podium hello world — business messaging and communication platform integration. Use when working with Podium API for messaging, reviews, or payments.
Podium install auth — business messaging and communication platform integration. Use when working with Podium API for messaging, reviews, or payments.
Podium local dev loop — business messaging and communication platform integration. Use when working with Podium API for messaging, reviews, or payments.
Podium performance tuning — business messaging and communication platform integration. Use when working with Podium API for messaging, reviews, or payments.
Podium upgrade migration — business messaging and communication platform integration. Use when working with Podium API for messaging, reviews, or payments.
Podium webhooks events — business messaging and communication platform integration. Use when working with Podium API for messaging, reviews, or payments.
Diagnose and fix common PostHog errors: events not appearing, flags returning undefined, 401/429 errors, SDK initialization failures, and identity issues.